DUDPA-TATD: A Lightweight Privacy-Preserving Anomaly Traffic Detection Method for Edge Computing Scenarios

In the field of network security, anomaly traffic detection is a key technology for identifying network attacks. It detects abnormal behavior and counteracts it by monitoring changes in traffic patterns. Deep learning-based methods significantly improve detection performance due to their ability to efficiently learn and extract complex feature representations. However, these methods require large amounts of data for training, which exacerbates the risk of privacy breaches and increases training time consumption. This paper proposes an anomaly traffic detection method based on differential privacy and temporal convolutional networks, named DUDPA-TATD. DUDPA-TATD consists of two components: the Dynamic Update Strategy with Differential Privacy Protection Laplace Mechanism (DUDPA) and the Temporal Aggregation Traffic Detection network based on Temporal Convolutional Networks (TATD). DUDPA gradually adjusts the privacy protection strategy according to the inference rules of TATD, while TATD enhances the learning of macro and micro differences in time-series data by aggregating key features, further improving detection performance. We conducted experiments on two public datasets. Compared with baseline methods, extensive experiments on the DAPT2020 and SMAP datasets demonstrate that our DUDPA-TATD not only exhibits superior detection performance but also requires less average training time than most baseline methods, qualifying it as a lightweight detection model.